{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EMDJGDGQIR4PQZFZ7CK4ZMGGUN","short_pith_number":"pith:EMDJGDGQ","schema_version":"1.0","canonical_sha256":"2306930cd04478f864b9f895ccb0c6a36e2861fb61c00c5e5b6acd306116974f","source":{"kind":"arxiv","id":"2501.18487","version":1},"attestation_state":"computed","paper":{"title":"Track-On: Transformer-based Online Point Tracking with Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatma G\\\"uney, G\\\"orkay Aydemir, Weidi Xie, Xiongyi Cai","submitted_at":"2025-01-30T17:04:11Z","abstract_excerpt":"In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online tracking on a frame-by-frame basis, making it suitable for real-world, streaming scenarios. Specifically, we introduce Track-On, a simple transformer-based model designed for online long-term point tracking. Unlike prior methods that depend on full temporal modeling, our model processes video frames causally without access to future frames, leveraging two m"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.18487","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T17:04:11Z","cross_cats_sorted":[],"title_canon_sha256":"1f2dc4ed73a07dd5f8db442225c96e64dd5262ec9d97c8bc42f60c0e8de1d71d","abstract_canon_sha256":"b8535e1df822bedc5dae20cd6a64b4dfdbfb2828d0b48434ec225e9251bc9470"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:34.679377Z","signature_b64":"C+GolNDiB9yUkDo4wfiJoAfPVHS6LLZhEh1B1/hgE2bqdDXx+RTnWNsZ9oZ54zRRK6Qe5W6mLYMGmkGblLUUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2306930cd04478f864b9f895ccb0c6a36e2861fb61c00c5e5b6acd306116974f","last_reissued_at":"2026-07-05T10:07:34.678942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:34.678942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Track-On: Transformer-based Online Point Tracking with Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatma G\\\"uney, G\\\"orkay Aydemir, Weidi Xie, Xiongyi Cai","submitted_at":"2025-01-30T17:04:11Z","abstract_excerpt":"In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online tracking on a frame-by-frame basis, making it suitable for real-world, streaming scenarios. Specifically, we introduce Track-On, a simple transformer-based model designed for online long-term point tracking. Unlike prior methods that depend on full temporal modeling, our model processes video frames causally without access to future frames, leveraging two m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18487","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.18487/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.18487","created_at":"2026-07-05T10:07:34.678997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.18487v1","created_at":"2026-07-05T10:07:34.678997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18487","created_at":"2026-07-05T10:07:34.678997+00:00"},{"alias_kind":"pith_short_12","alias_value":"EMDJGDGQIR4P","created_at":"2026-07-05T10:07:34.678997+00:00"},{"alias_kind":"pith_short_16","alias_value":"EMDJGDGQIR4PQZFZ","created_at":"2026-07-05T10:07:34.678997+00:00"},{"alias_kind":"pith_short_8","alias_value":"EMDJGDGQ","created_at":"2026-07-05T10:07:34.678997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.15094","citing_title":"BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Tracking","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN","json":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN.json","graph_json":"https://pith.science/api/pith-number/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/graph.json","events_json":"https://pith.science/api/pith-number/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/events.json","paper":"https://pith.science/paper/EMDJGDGQ"},"agent_actions":{"view_html":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN","download_json":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN.json","view_paper":"https://pith.science/paper/EMDJGDGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.18487&json=true","fetch_graph":"https://pith.science/api/pith-number/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/graph.json","fetch_events":"https://pith.science/api/pith-number/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/action/storage_attestation","attest_author":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/action/author_attestation","sign_citation":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/action/citation_signature","submit_replication":"https://pith.science/pith/EMDJGDGQIR4PQZFZ7CK4ZMGGUN/action/replication_record"}},"created_at":"2026-07-05T10:07:34.678997+00:00","updated_at":"2026-07-05T10:07:34.678997+00:00"}